Compare / Gemini 3.8 Flash vs Mistral Small 4
Gemini 3.8 Flash vs Mistral Small 4
22 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Gemini 3.8 Flash | Mistral Small 4 |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0154 | $0.0039 |
| BulletBenchmeasured by us | Games lost on time% of games | 50.0% | 25.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.0% | 0.6% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 1,068 | 367 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.8 s | 0.6 s |
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0041 | $0.0041 |
| BulletBenchmeasured by us | Games lost on time% of games | 83.3% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.0% | 1.0% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 197 | 571 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.8 s | 0.6 s |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 76.3 | 26.6 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 40.9 | 11.3 |
| Artificial Analysisreported | GPQA Diamond% of questions | 95.3% | 76.9% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 47.8% | 9.9% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 84.0% | 49.7% |
| Artificial Analysisreported | SciCode% of problems | 56.6% | 38.8% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 87.6% | 21.0% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 19.7% | 0.0% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 45.8% | 4.9% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 13.0% | 22.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.34 | 0.31 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 78.5 | 40.3 |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.